Image/video coding using content-aware resizing

2014 Fiscal Year Final Research Report

• Project/Area Number: 24760288
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Multi-year Fund
• Research Field: Communication/Network engineering
• Research Institution: Tokyo University of Agriculture and Technology
• Principal Investigator: TANAKA Yuichi 東京農工大学, 工学(系)研究科(研究院), 准教授 (10547029)
• Project Period (FY): 2012-04-01 – 2015-03-31
• Keywords: 映像符号化 / ウェーブレット・フィルタバンク / リターゲティング

Outline of Final Research Achievements

We realized ROI (region of interest) image/video coding using content-aware resizing. Content-aware resizing is an image resizing method which has emerged in computer graphics. It automatically extracts ROI from an image and resizes it so that the resulting image preserves ROI as large as possible. We integrated it into image coding, and extended the method to video coding.
In experimental results, content-aware image/video coding was realized with a small amount of overhead bitrates from image/video coding without considering ROI. We further extended our approach to other image processing applications.

Free Research Field

信号処理